- 32 analyses: each label kept, rewritten or removed by its analyst (section Requalification of the report; mm magnitudes where the targets have them) - SNCF01 x3, WILDSTRUBEL 2026-09-01 -> 2026-10-06 x3: verified from their existing labels under the new rules - long labels (no analysis): auto/analyses/long-labels/<STATION>/; NORDEND-169 and -195 run to 07/11, so NORDEND-283 and -284 (their continuation) are removed - reading-rules.md, stations.md: the citations of removed or rewritten labels point to their successor, or to [expert] Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
47 lines
2.6 KiB
Python
47 lines
2.6 KiB
Python
"""For each studied target, over a window: corr minus the median of the healthy targets at the same instant
|
|
(common mode removed), then its own noise (median abs consecutive diff of the raw corr, as ranges.py) and the
|
|
measurements whose residual deviates from its rolling-1d median by more than K noises. Also the healthy targets,
|
|
leave-one-out, for comparison. Usage: specific.py START END SENSOR[,SENSOR] [K]"""
|
|
import sys, statistics
|
|
from datetime import timedelta
|
|
sys.path.insert(0, "tools/scripts")
|
|
import data, common
|
|
start, end = data.parse_time(sys.argv[1]), data.parse_time(sys.argv[2])
|
|
studied = sys.argv[3].split(",")
|
|
K = float(sys.argv[4]) if len(sys.argv) > 4 else 5
|
|
by = data.load("data/NIEDERHORN")
|
|
healthy = ["PWD_RMP_B12_020_C09","PWD_IMP_B08_025_C09","PWD_RMP_B15_018_C09","PWD_IMP_B07_017_C09","PWD_RMP_B12_018_C09",
|
|
"PWD_RMP_B12_017_C09","PWD_RMP_B15_019_C09","PWD_RMP_B15_020_C09","PWD_RMP_B17_026_C09",
|
|
"e02","e06","e09","e10","e13","e14","e15"]
|
|
win = {s: [m for m in data.filter_window(ms, start, end)] for s, ms in by.items()}
|
|
def series(s, col):
|
|
return {m["t"]: m[col] for m in win[s] if m[col] is not None}
|
|
for col in ("corr_x", "corr_y"):
|
|
H = {s: series(s, col) for s in healthy}
|
|
print(f"== {col} (K={K}, rolling ±1d, common mode = median of healthy targets)")
|
|
for s in studied + healthy:
|
|
own = series(s, col)
|
|
if len(own) < 10:
|
|
print(f"{s:22s} n={len(own)} (no curve)"); continue
|
|
noise = common.own_noise([own[t] for t in sorted(own)])
|
|
res = {}
|
|
for t, v in own.items():
|
|
others = [H[h][t] for h in healthy if h != s and t in H[h]]
|
|
if len(others) >= 5:
|
|
res[t] = v - statistics.median(others)
|
|
ts = sorted(res)
|
|
out = []
|
|
for t in ts:
|
|
nb = [res[u] for u in ts if u != t and abs((u - t).total_seconds()) <= 86400]
|
|
if len(nb) < 5: continue
|
|
d = (res[t] - statistics.median(nb)) / noise
|
|
if abs(d) > K: out.append((t, d))
|
|
ext = max(out, key=lambda x: abs(x[1])) if out else None
|
|
kmm = None
|
|
mm = [m for m in win[s] if m[col + "_mm"] is not None and m[col] not in (None, 0)]
|
|
if mm: kmm = mm[0][col + "_mm"] / mm[0][col]
|
|
days = len({t.date() for t, _ in out})
|
|
e = f"extreme {ext[1]:+.1f} noises ({ext[1]*noise:+.3f} px" + (f", {ext[1]*noise*kmm:+.2f} mm" if kmm else "") + f") at {data.iso(ext[0])}" if ext else ""
|
|
tag = "*" if s in studied else " "
|
|
print(f"{tag}{s:22s} n={len(own):4d} noise={noise:.4f} beyond: {len(out):3d} ({100*len(out)/max(1,len(res)):4.1f} %) on {days:2d} days {e}")
|